Chest radiographic features of human metapneumovirus infection in pediatric patients

Abstract

Background Human metapneumovirus (HMPV) was identified in 2001 and is a common cause of acute respiratory illness in young children. The radiologic characteristics of laboratory-confirmed HMPV acute respiratory illness in young children have not been systematically assessed. Objective We systematically evaluated the radiographic characteristics of acute respiratory illness associated with HMPV in a prospective cohort of pediatric patients. Materials and methods We included chest radiographs from children <5 years old with acute respiratory illness who were enrolled in the prospective New Vaccine Surveillance Network (NVSN) study from 2003 to 2009 and were diagnosed with HMPV by reverse transcription-polymerase chain reaction (RT-PCR). Of 215 HMPV-positive subjects enrolled at our tertiary care children’s hospital, 68 had chest radiographs obtained by the treating clinician that were available for review. Two fellowship-trained pediatric radiologists, independently and then in consensus, retrospectively evaluated these chest radiographs for their radiographic features. Results Parahilar opacities were the most commonly observed abnormality, occurring in 87% of children with HMPV. Hyperinflation also occurred frequently (69%). Atelectasis (40%) and consolidation (18%) appeared less frequently. Pleural effusion and pneumothorax were not seen on any radiographs. Conclusion The clinical presentations of HMPV include bronchiolitis, croup and pneumonia. Dominant chest radiographic abnormalities include parahilar opacities and hyperinflation, with occasional consolidation. Recognition of the imaging patterns seen with common viral illnesses like respiratory syncytial virus (RSV) and HMPV might facilitate diagnosis and limit unnecessary antibiotic treatment.

Role of Hybrid Deep Neural Networks (HDNNs), Computed Tomography, and Chest X-rays for the Detection of COVID-19

“…Particularly, the data from different modalities complement each other. Therefore, it can be said that this is a general phenomenon, which is also evident in many earlier studies, involving multi-model/multi-data studies [25,26].…”

“…Particularly, the data from different modalities complement each other. Therefore, it can be said that this is a general phenomenon, which is also evident in many earlier studies, involving multi-model/multi-data studies [ 25 , 26 ]. Multimodal dataset (CT and X-rays images), which provides more accurate and reliable results in comparison to the single CT image data set or single X-ray datasets.…”

“…These two models are deep learning-based models, which is a sub-field of artificial intelligence. The two deep learning models are well-suited to classifying, processing, and making predictions, which resulted in extraordinary performance in automatic feature extraction from images datasets [ 23 , 26 ]. We picked the CNN model, because of their automated feature learning, and used LSTM to deal with the vanishing gradient problem, which occurs when training neural networks.…”

Respiratory Virus Infections in Hematopoietic Cell Transplant Recipients

“…Chest x-rays are generally not recommended because lack of sensitivity but CT should be performed to evaluate LRI. In children, chest x-rays do not provide specific information in case of HMPV infection where common findings include hyperinflation, atelectasis and perihilar opacities (Hilmes et al, 2017).…”

Human metapneumovirus infection: Diagnostic impact of radiologic imaging

“…Radiologic findings of hMPV infection have not been reported to be different from other viral pathogens in studies with high sample sizes; however, it has been reported that studies including radiologic findings of hMPV infections were commonly done among immunocompromised hosts …”